patch 'net/gve: copy data to QPL buffer when mbuf read does not' has been queued to stable release 24.11.7

[luca.boccassi at gmail.com]

Hi,

FYI, your patch has been queued to stable release 24.11.7

Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before 07/15/26. So please
shout if anyone has objections.

Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.

Queued patches are on a temporary branch at:
https://github.com/bluca/dpdk-stable

This queued commit can be viewed at:
https://github.com/bluca/dpdk-stable/commit/316e0ee914c11e488e5c287a91fea7985e0346ad

Thanks.

Luca Boccassi

---
>From 316e0ee914c11e488e5c287a91fea7985e0346ad Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash at google.com>
Date: Wed, 8 Jul 2026 21:07:31 -0700
Subject: [PATCH] net/gve: copy data to QPL buffer when mbuf read does not

[ upstream commit c75da01101658480d31fb2a96351b99418600c4f ]

The rte_pktmbuf_read method does not guarantee that data will be copied
from an mbuf. If the requested data is all contiguous, the method will
instead return a pointer to the memory location within the buffer that
should be read from, leaving the destination buffer empty.

This is problematic for TSO/multi-segment TX packets which only make use
of two mbufs. If all data in the second mbuf is contiguous, the data
will not be read to QPL memory.

Update the QPL copy logic to copy if the rte_pktmbuf_read does not.

Fixes: a46583cf43c8 ("net/gve: support Rx/Tx")

Signed-off-by: Joshua Washington <joshwash at google.com>
Reviewed-by: Jasper Tran O'Leary <jtranoleary at google.com>
---
 drivers/net/gve/gve_tx.c | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/net/gve/gve_tx.c b/drivers/net/gve/gve_tx.c
index 2d6a4272cc..ea9977ef5f 100644
--- a/drivers/net/gve/gve_tx.c
+++ b/drivers/net/gve/gve_tx.c
@@ -255,10 +255,10 @@ gve_tx_burst_qpl(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 	struct rte_mbuf **sw_ring = txq->sw_ring;
 	uint16_t mask = txq->nb_tx_desc - 1;
 	uint16_t tx_id = txq->tx_tail & mask;
-	uint64_t ol_flags, addr, fifo_addr;
 	uint32_t tx_tail = txq->tx_tail;
 	struct rte_mbuf *tx_pkt, *first;
 	uint16_t sw_id = txq->sw_tail;
+	uint64_t ol_flags, fifo_addr;
 	uint16_t nb_used, i;
 	uint64_t bytes = 0;
 	uint16_t nb_tx = 0;
@@ -273,6 +273,9 @@ gve_tx_burst_qpl(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 		gve_tx_clean_swr_qpl(txq);
 
 	for (nb_tx = 0; nb_tx < nb_pkts; nb_tx++) {
+		const void *mbuf_header_addr;
+		void *qpl_write_addr;
+
 		tx_pkt = *tx_pkts++;
 		ol_flags = tx_pkt->ol_flags;
 
@@ -306,7 +309,6 @@ gve_tx_burst_qpl(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 			if (!is_fifo_avail(txq, hlen))
 				goto end_of_tx;
 		}
-		addr = (uint64_t)(tx_pkt->buf_addr) + tx_pkt->data_off;
 		fifo_addr = gve_tx_alloc_from_fifo(txq, tx_id, hlen);
 
 		/* For TSO, check if there's enough fifo space for data first */
@@ -317,26 +319,32 @@ gve_tx_burst_qpl(void *tx_queue, struct rte_mbuf **tx_pkts, uint16_t nb_pkts)
 					goto end_of_tx;
 			}
 		}
-		if (tx_pkt->nb_segs == 1 || ol_flags & RTE_MBUF_F_TX_TCP_SEG)
-			rte_memcpy((void *)(size_t)(fifo_addr + txq->fifo_base),
-				   (void *)(size_t)addr, hlen);
-		else
-			rte_pktmbuf_read(tx_pkt, 0, hlen,
-					 (void *)(size_t)(fifo_addr + txq->fifo_base));
+
+		qpl_write_addr = (void *)(size_t)(fifo_addr + txq->fifo_base);
+		mbuf_header_addr = rte_pktmbuf_read(tx_pkt, 0, hlen, qpl_write_addr);
+
+		/* Header data is linear in the mbuf head. Copy directly. */
+		if (mbuf_header_addr != qpl_write_addr)
+			rte_memcpy(qpl_write_addr, mbuf_header_addr, hlen);
+
 		gve_tx_fill_pkt_desc(txd, tx_pkt, nb_used, hlen, fifo_addr);
 
 		if (ol_flags & RTE_MBUF_F_TX_TCP_SEG) {
+			const void *mbuf_payload_addr;
+
 			tx_id = (tx_id + 1) & mask;
 			txd = &txr[tx_id];
-			addr = (uint64_t)(tx_pkt->buf_addr) + tx_pkt->data_off + hlen;
 			fifo_addr = gve_tx_alloc_from_fifo(txq, tx_id, tx_pkt->pkt_len - hlen);
-			if (tx_pkt->nb_segs == 1)
-				rte_memcpy((void *)(size_t)(fifo_addr + txq->fifo_base),
-					   (void *)(size_t)addr,
+			qpl_write_addr = (void *)(size_t)(txq->fifo_base + fifo_addr);
+			mbuf_payload_addr = rte_pktmbuf_read(tx_pkt, hlen, tx_pkt->pkt_len - hlen,
+							     qpl_write_addr);
+
+			/* Payload data is contiguous. Take the offset from the
+			 * read request and copy from there.
+			 */
+			if (mbuf_payload_addr != qpl_write_addr)
+				rte_memcpy(qpl_write_addr, mbuf_payload_addr,
 					   tx_pkt->pkt_len - hlen);
-			else
-				rte_pktmbuf_read(tx_pkt, hlen, tx_pkt->pkt_len - hlen,
-						 (void *)(size_t)(fifo_addr + txq->fifo_base));
 
 			gve_tx_fill_seg_desc(txd, ol_flags, tx_offload,
 					     tx_pkt->pkt_len - hlen, fifo_addr);
-- 
2.47.3

---
  Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- -	2026-07-13 18:17:05.893142253 +0100
+++ 0008-net-gve-copy-data-to-QPL-buffer-when-mbuf-read-does-.patch	2026-07-13 18:17:05.574282834 +0100
@@ -1 +1 @@
-From c75da01101658480d31fb2a96351b99418600c4f Mon Sep 17 00:00:00 2001
+From 316e0ee914c11e488e5c287a91fea7985e0346ad Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit c75da01101658480d31fb2a96351b99418600c4f ]
+
@@ -18 +19,0 @@
-Cc: stable at dpdk.org
@@ -27 +28 @@
-index 59c82b04ed..c0400b07bf 100644
+index 2d6a4272cc..ea9977ef5f 100644